{"id":"https://openalex.org/W4416203751","doi":"https://doi.org/10.1145/3712285.3759867","title":"MaverIQ: Fingerprint-Guided Extrapolation and Fragmentation-Aware Layering for Intent-Based LLM Serving","display_name":"MaverIQ: Fingerprint-Guided Extrapolation and Fragmentation-Aware Layering for Intent-Based LLM Serving","publication_year":2025,"publication_date":"2025-11-12","ids":{"openalex":"https://openalex.org/W4416203751","doi":"https://doi.org/10.1145/3712285.3759867"},"language":null,"primary_location":{"id":"doi:10.1145/3712285.3759867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3712285.3759867","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116016294","display_name":"Dimitrios Liakopoulos","orcid":"https://orcid.org/0009-0003-9444-2407"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dimitrios Liakopoulos","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113099539","display_name":"Prasoon Sinha","orcid":"https://orcid.org/0000-0002-5538-8829"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasoon Sinha","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116016295","display_name":"Tianrui Hu","orcid":"https://orcid.org/0009-0007-0246-7826"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianrui Hu","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101640757","display_name":"Myungjin Lee","orcid":"https://orcid.org/0000-0003-2360-7019"},"institutions":[{"id":"https://openalex.org/I151281966","display_name":"Cisco Systems (China)","ror":"https://ror.org/02qy75381","country_code":"CN","type":"company","lineage":["https://openalex.org/I135428043","https://openalex.org/I151281966"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Myungjin Lee","raw_affiliation_strings":["Cisco Systems, Bellevue, USA"],"affiliations":[{"raw_affiliation_string":"Cisco Systems, Bellevue, USA","institution_ids":["https://openalex.org/I151281966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031510918","display_name":"Neeraja J. Yadwadkar","orcid":"https://orcid.org/0009-0007-7556-3069"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neeraja J. Yadwadkar","raw_affiliation_strings":["The University of Texas at Austin, Austin, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5116016294"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.8331,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.93072849,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1676","last_page":"1696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.09290000051259995,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.09290000051259995,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.07890000194311142,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.07569999992847443,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.8424999713897705},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5509999990463257},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.516700029373169},{"id":"https://openalex.org/keywords/extrapolation","display_name":"Extrapolation","score":0.5029000043869019},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.3425000011920929},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.3321000039577484},{"id":"https://openalex.org/keywords/automation","display_name":"Automation","score":0.33180001378059387}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8424999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.516700029373169},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.5029000043869019},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33880001306533813},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33469998836517334},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.33180001378059387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C176055353","wikidata":"https://www.wikidata.org/wiki/Q1402114","display_name":"Layering","level":2,"score":0.2815000116825104},{"id":"https://openalex.org/C2781018962","wikidata":"https://www.wikidata.org/wiki/Q5164884","display_name":"Container (type theory)","level":2,"score":0.2777999937534332},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3712285.3759867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3712285.3759867","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3712285.3759867","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2765982206","https://openalex.org/W3034999214","https://openalex.org/W3130716829","https://openalex.org/W3188270315","https://openalex.org/W3204998121","https://openalex.org/W3210432446","https://openalex.org/W4220741164","https://openalex.org/W4294433898","https://openalex.org/W4308426152","https://openalex.org/W4312681979","https://openalex.org/W4321636575","https://openalex.org/W4365128500","https://openalex.org/W4366341968","https://openalex.org/W4376652719","https://openalex.org/W4386768656","https://openalex.org/W4387321091","https://openalex.org/W4388874804","https://openalex.org/W4388979610","https://openalex.org/W4389519278","https://openalex.org/W4389524555","https://openalex.org/W4394892775","https://openalex.org/W4394998727","https://openalex.org/W4395020691","https://openalex.org/W4395073472","https://openalex.org/W4395112660","https://openalex.org/W4395117922","https://openalex.org/W4401044069","https://openalex.org/W4401211704","https://openalex.org/W4401211883","https://openalex.org/W4402683730","https://openalex.org/W4404057314","https://openalex.org/W4404400583","https://openalex.org/W4404401017","https://openalex.org/W4404401018","https://openalex.org/W4405755255","https://openalex.org/W4405756183","https://openalex.org/W4405756215","https://openalex.org/W4405756292","https://openalex.org/W4407196897","https://openalex.org/W4407218342","https://openalex.org/W4408847395","https://openalex.org/W4408848075","https://openalex.org/W4408848702","https://openalex.org/W4408891420","https://openalex.org/W4408893361"],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"are":[4],"becoming":[5],"ubiquitous":[6],"across":[7],"industries,":[8],"where":[9],"applications":[10],"demand":[11],"they":[12,53],"fulfill":[13],"diverse":[14,87],"user":[15,88],"intents.":[16,44,89],"However,":[17],"developers":[18],"currently":[19],"face":[20],"the":[21,63,75],"challenge":[22],"of":[23,29,79],"manually":[24],"exploring":[25],"numerous":[26],"deployment":[27,83],"configurations\u2014combinations":[28],"parallelism":[30],"and":[31,40,50,59],"compression":[32],"techniques":[33],"that":[34],"impact":[35],"resource":[36,65],"usage,":[37],"latency,":[38],"cost,":[39],"accuracy\u2014to":[41],"meet":[42],"these":[43,80],"Previous":[45],"works":[46],"automate":[47],"configuration":[48,84],"selection":[49],"deployment,":[51],"but,":[52],"(a)":[54],"rely":[55],"on":[56],"expensive":[57],"profiling,":[58],"(b)":[60],"suboptimally":[61],"utilize":[62],"fragmented":[64],"availability":[66],"in":[67],"multi-tenant":[68],"GPU":[69],"clusters,":[70],"inflating":[71],"operational":[72],"costs":[73],"for":[74],"provider.":[76],"Moreover,":[77],"none":[78],"solutions":[81],"tailors":[82],"decisions":[85],"to":[86]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-12T00:00:00"}